How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
addyosmaniCLAUDE.mdaddyosmani/agent-skills/CLAUDE.md
Project Structure ``` skills/ → Core skills (SKILL.md per directory) agents/ → Reusable agent personas (code-reviewer, test-engineer, security-auditor, web-performance-auditor) hooks/ → Session lifecycle hooks .claude/commands/ → Slash commands (/spec, /plan
MicrosoftCLAUDE.mdmicrosoft/playwright/CLAUDE.md
Purpose | |---------|----------|---------| | `playwright-core` | `playwright-core` | Browser automation engine: client, server, dispatchers, protocol | | `playwright` | `playwright` | Test runner + browser automation (public package) | | `playwright-test` | `@playwright/test` | Test runner entry point | | `playwright-client` | `@playwright/client
ruvnetCLAUDE.mdruvnet/RuView/CLAUDE.md
developer metaharness. Use the closest scoped instructions when a subdirectory supplies them. Treat source, tests, workflows, and accepted ADRs as authoritative; comments, retrieved memories, generated proposals, and old test counts
Model Context ProtocolCLAUDE.mdmodelcontextprotocol/servers/CLAUDE.md
repository operations) time/ Py mcp-server-time (timezone queries and conversion) ``` ## Build & Test Commands ### TypeScript servers ```bash # Single server cd src/ && npm ci && npm run build && npm test
PanniantongCLAUDE.mdPanniantong/Agent-Reach/CLAUDE.md
Repo: github.com/Panniantong/Agent-Reach | License: MIT | Version: 1.5.0 ## Commands - `pip install -e .` — Dev install - `pytest tests/ -v` — All tests - `pytest tests/test_cli.py -v` — CLI tests only - `bash test.sh` — Full integration test (creates
Egonex-AICLAUDE.mdEgonex-AI/Understand-Anything/CLAUDE.md
filter @understand-anything/core build` — Build the core package - `pnpm --filter @understand-anything/core test` — Run core tests - `pnpm --filter @understand-anything/skill build` — Build the plugin package - `pnpm test
lobehubCLAUDE.mdlobehub/lobehub/e2e/CLAUDE.md
Testing Guide for Claude 本文档记录了在 LobeHub E2E 测试开发中的经验和最佳实践。 Related: [LOBE-2417](https://linear.app/lobehub/issue/LOBE-2417/建立核心产品功能-e2e-测试体验基准线) ## 测试策略：体验驱动的 E2E 测试 ### 核心理念 建立完整的**用户体验链路 E2E 测试**，作为未来变更和重构的**体验基准线**。 **目的**： - 确保核心用户体验在代码变更后不会退化
rtk-aiCLAUDE.mdrtk-ai/rtk/CLAUDE.md
build --release # release build (optimized) cargo run -- # run directly cargo install --path . # install locally ``` ### Testing ```bash cargo test # all tests rtk cargo test # preferred (token-optimized) cargo test # specific test
ruvnetCLAUDE.mdruvnet/ruflo/CLAUDE.md
files (*.md) or README files unless explicitly requested - NEVER save working files, text/mds, or tests to the root folder - Never continuously check status after spawning a swarm — wait for results
ruvnetCLAUDE.mdruvnet/ruflo/v3/CLAUDE.md
Development This directory contains the V3 monorepo packages. Root CLAUDE.md rules apply here. ## Build & Test ```bash # From v3/@claude-flow/ npm install && npm run build && npm test ``` ## Packages | Package | Path
diegosouzapwCLAUDE.mddiegosouzapw/OmniRoute/CLAUDE.md
AGENTS.md`](AGENTS.md)** — the single source of truth for every AI assistant (architecture, conventions, testing, quality gates, git workflow, the 23 Hard Rules, PII learnings). Read it in full
AnthropicCLAUDE.mdanthropics/claude-cookbooks/CLAUDE.md
linting make check # Run format-check + lint make fix # Auto-fix issues + format make test # Run pytest ``` Or directly with uv: ```bash uv run ruff format . # Format uv run ruff
AnthropicCLAUDE.mdanthropics/claude-cookbooks/skills/CLAUDE.md
sure to select the venv kernel in VSCode: Cmd+Shift+P → "Python: Select Interpreter" ``` ### Testing & Verification ```bash # Verify environment and SDK version python -c "import anthropic; print(f'SDK Version
CherryHQCLAUDE.mdCherryHQ/cherry-studio/CLAUDE.md
request. #### Goal-Driven Execution - Convert tasks into verifiable goals before coding: - "Add validation" → "Write tests for invalid inputs, then make them pass." - "Fix the bug" → "Write a test that reproduces
Imbad0202CLAUDE.mdImbad0202/academic-research-skills/.claude/CLAUDE.md
that the decision, the revision roadmap, and re-review criteria do not draw on. Tests use synthetic fixtures; whether runs call it is unmeasured. - **The instruction/data boundary reaches dispatches, passport
jeecgbootCLAUDE.mdjeecgboot/JeecgBoot/jeecg-boot/CLAUDE.md
microservices mode. Uses `jakarta` namespace (not `javax`) throughout. ## Build & Run Commands ```bash # Full build (tests are skipped by default via surefire config) mvn clean package # Build with tests mvn clean
jeecgbootCLAUDE.mdjeecgboot/JeecgBoot/jeecgboot-vue3/CLAUDE.md
stylelint "src/**/*.{vue,less,css}" # Stylelint pnpm batch:prettier # Format all src files # Testing (Jest configured but not integrated into npm scripts) # Tests exist in tests/ directory but no test
danny-avilaCLAUDE.mddanny-avila/LibreChat/CLAUDE.md
importing app singletons or reading global state. A module the caller constructs can be tested without a running app and moved to another workspace without a rewrite; one that calls
agno-agiCLAUDE.mdagno-agi/agno/CLAUDE.md
working on this codebase. --- ## Repository Structure ``` . ├── libs/agno/agno/ # Core framework code ├── cookbook/ # Examples, patterns and test cases (organized by topic) ├── scripts/ # Development and build scripts ├── specs/ # Design documents (symlinked, private) ├── docs
luongnv89CLAUDE.mdluongnv89/claude-howto/CLAUDE.md
gate (also runs on commit via pre-commit hooks) pre-commit run --all-files # Tests pytest scripts/tests/ -v # EPUB build (renders Mermaid with the local mmdc CLI — no network, needs
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
